Streaming Graph Neural Networks via Continual Learning

• URL: http://arxiv.org/abs/2009.10951v2
• Date: Fri, 4 Dec 2020 06:56:16 GMT
• Title: Streaming Graph Neural Networks via Continual Learning
• Authors: Junshan Wang, Guojie Song, Yi Wu, Liang Wang
• Abstract summary: Graph neural networks (GNNs) have achieved strong performance in various applications. In this paper, we propose a streaming GNN model based on continual learning. We show that our model can efficiently update model parameters and achieve comparable performance to model retraining.
• Score: 31.810308087441445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) have achieved strong performance in various applications. In the real world, network data is usually formed in a streaming fashion. The distributions of patterns that refer to neighborhood information of nodes may shift over time. The GNN model needs to learn the new patterns that cannot yet be captured. But learning incrementally leads to the catastrophic forgetting problem that historical knowledge is overwritten by newly learned knowledge. Therefore, it is important to train GNN model to learn new patterns and maintain existing patterns simultaneously, which few works focus on. In this paper, we propose a streaming GNN model based on continual learning so that the model is trained incrementally and up-to-date node representations can be obtained at each time step. Firstly, we design an approximation algorithm to detect new coming patterns efficiently based on information propagation. Secondly, we combine two perspectives of data replaying and model regularization for existing pattern consolidation. Specially, a hierarchy-importance sampling strategy for nodes is designed and a weighted regularization term for GNN parameters is derived, achieving greater stability and generalization of knowledge consolidation. Our model is evaluated on real and synthetic data sets and compared with multiple baselines. The results of node classification prove that our model can efficiently update model parameters and achieve comparable performance to model retraining. In addition, we also conduct a case study on the synthetic data, and carry out some specific analysis for each part of our model, illustrating its ability to learn new knowledge and maintain existing knowledge from different perspectives.

Related papers

• Robust Knowledge Adaptation for Dynamic Graph Neural Networks [61.8505228728726]
  We propose Ada-DyGNN: a robust knowledge Adaptation framework via reinforcement learning for Dynamic Graph Neural Networks. Our approach constitutes the first attempt to explore robust knowledge adaptation via reinforcement learning. Experiments on three benchmark datasets demonstrate that Ada-DyGNN achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-07-22T02:06:53Z)
• Data-Free Adversarial Knowledge Distillation for Graph Neural Networks [62.71646916191515]
  We propose the first end-to-end framework for data-free adversarial knowledge distillation on graph structured data (DFAD-GNN) To be specific, our DFAD-GNN employs a generative adversarial network, which mainly consists of three components: a pre-trained teacher model and a student model are regarded as two discriminators, and a generator is utilized for deriving training graphs to distill knowledge from the teacher model into the student model. Our DFAD-GNN significantly surpasses state-of-the-art data-free baselines in the graph classification task.
  arXiv  Detail & Related papers  (2022-05-08T08:19:40Z)
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach [80.8446673089281]
  We propose a new learning paradigm with graph representation and learning. Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
  arXiv  Detail & Related papers  (2021-10-09T09:02:45Z)
• Sparsifying the Update Step in Graph Neural Networks [15.446125349239534]
  We study the effect of sparsification on the trainable part of MPNNs known as the Update step. Specifically, we propose the ExpanderGNN model with a tuneable sparsification rate and the Activation-Only GNN, which has no linear transform in the Update step. Our novel benchmark models enable a better understanding of the influence of the Update step on model performance.
  arXiv  Detail & Related papers  (2021-09-02T13:06:34Z)
• A Deep Latent Space Model for Graph Representation Learning [10.914558012458425]
  We propose a Deep Latent Space Model (DLSM) for directed graphs to incorporate the traditional latent variable based generative model into deep learning frameworks. Our proposed model consists of a graph convolutional network (GCN) encoder and a decoder, which are layer-wise connected by a hierarchical variational auto-encoder architecture. Experiments on real-world datasets show that the proposed model achieves the state-of-the-art performances on both link prediction and community detection tasks.
  arXiv  Detail & Related papers  (2021-06-22T12:41:19Z)
• The World as a Graph: Improving El Ni\~no Forecasts with Graph Neural Networks [0.00916150060695978]
  We propose the first application of graph neural networks to seasonal forecasting. Our model, graphino, outperforms state-of-the-art deep learning-based models for forecasts up to six months ahead.
  arXiv  Detail & Related papers  (2021-04-11T19:55:55Z)
• Temporal Knowledge Graph Forecasting with Neural ODE [19.64877769280854]
  We extend the idea of continuum-depth models to time-evolving multi-relational graph data. Our model captures temporal information through NODE and structural information through a Graph Neural Network (GNN) Our model achieves a continuous model in time and efficiently learns node representation for future prediction.
  arXiv  Detail & Related papers  (2021-01-13T15:49:48Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)
• Lifelong Learning of Graph Neural Networks for Open-World Node Classification [3.364554138758565]
  Real-world graphs are often evolving over time and even new classes may arise. We model these challenges as an instance of lifelong learning. In this work, we systematically analyze the influence of implicit and explicit knowledge.
  arXiv  Detail & Related papers  (2020-06-25T14:03:31Z)
• Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case [93.37576644429578]
  Graph neural networks (GNNs) have made great progress recently on learning from graph-structured data in practice. We provide a theoretically-grounded generalizability analysis of GNNs with one hidden layer for both regression and binary classification problems.
  arXiv  Detail & Related papers  (2020-06-25T00:45:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.